Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15207
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Trudy."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically last names that start with "Tr"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ration
    -0.70
     liking
    -0.68
    WARE
    -0.67
     Nationwide
    -0.64
     directors
    -0.64
     buckle
    -0.64
     Jaguar
    -0.63
     trapping
    -0.62
     stopping
    -0.62
     controlling
    -0.61
    POSITIVE LOGITS
    anqu
    1.38
    imble
    1.35
    acey
    1.31
    istan
    1.26
    icky
    1.25
    agically
    1.25
    agic
    1.24
    umps
    1.23
    umper
    1.22
    icol
    1.20
    Activations Density 0.009%

    No Known Activations